package second;
 
import java.util.*;
 
public class OutputWordMess {
 
public static void main(String[] args) {
 
Vector allWord,noSameWord;
 
WordStatistic statistic=new WordStatistic();
 
statistic.setFileName("hello.txt");
 
statistic.WordStatistic();
 
allWord=statistic.getAllWord();
 
noSameWord=statistic.getNoSameWord();
 
System.out.println("共有"+allWord.size()+"个英文单词");
 
System.out.println("有"+noSameWord.size()+"个互不相同英文单词");
 
System.out.println("按出现的频率排列：");
 
int count[]=new int[noSameWord.size()];
 
for(int i=0;i
 
String s1=noSameWord.elementAt(i);
 
for(int j=0;j
 
String s2=allWord.elementAt(j);
 
if(s1.equals(s2))
 
count[i]++;
 
}
 
}
 
for(int m=0;m
 
for(int n=m+1;n
 
if(count[n]>count[m]){
 
String temp=noSameWord.elementAt(m);
 
noSameWord.setElementAt(noSameWord.elementAt(n), m);
 
noSameWord.setElementAt(temp, n);
 
int t=count[m];
 
count[m]=count[n];
 
count[n]=t;
 
}
 
}
 
}
 
for(int m=0;m
 
double frequency=(1.0*count[m])/allWord.size();
 
System.out.printf("%s:%-7.3f", noSameWord.elementAt(m),frequency);
 
}
 
}
 
}
 
import java.io.*;
 
import java.util.*;
 
public class WordStatistic {
 
Vector allWord,noSameWord;
 
File file=new File("english.txt");
 
Scanner sc=null;
 
String regex;
 
WordStatistic (){
 
allWord=new Vector();
 
noSameWord=new Vector();
 
regex="[\\s\\d\\p{Punct}]+";//正则表达式
 
try{
 
sc=new Scanner(file);
 
sc.useDelimiter(regex);
 
}
 
catch(IOException exp){
 
System.out.println(exp.toString());
 
}
 
}
 
void setFileName(String name){
 
file=new File(name);
 
try{
 
sc=new Scanner(file);
 
sc.useDelimiter(regex);
 
}
 
catch(IOException exp){
 
System.out.println(exp.toString());
 
}
 
}
 
void WordStatistic() {
 
// TODO Auto-generated method stub
 
try{
 
while(sc.hasNext()){
 
String word=sc.next();
 
allWord.add(word);
 
if(!noSameWord.contains(word))
 
noSameWord.add(word);
 
}
 
}
 
catch(Exception e){}
 
}
 
public VectorgetAllWord(){
 
return allWord;
 
}
 
public VectorgetNoSameWord(){
 
return noSameWord;
 
}
 
}

 
public class englishTest {
 
public static void main(String args[]) throws IOException {
 
BufferedReader buf= new BufferedReader(
 
new FileReader("d:/english.txt"));
 
BufferedWriter bufw= new BufferedWriter(
 
new FileWriter("d:/result.txt"));
 
StringBuffer sbuf = new StringBuffer();// 缓冲字符串
 
String line = null;
 
while ((line = buf.readLine()) != null) {
 
sbuf.append(line);
 
sbuf.append(" ");// 追加到缓冲字符串中
 
if (!line.isEmpty()) {// 去文本空行
 
bufw.newLine();
 
bufw.write(line);
 
}
 
}
 
buf.close();// 读取结束
 
String string1 = sbuf.toString().toLowerCase();// 转换成小写
 
Pattern expression = Pattern.compile("[a-zA-Z]+");// 定义正则表达式匹配单词
 
Matchermatcher = expression.matcher(string1);// 定义string1的匹配器
 
TreeMap myTreeMap = new TreeMap();// 创建树映射 存放键/值对
 
int n = 0;// 文章中单词总数
 
Object word = null;// 文章中的单词
 
Object num = null;// 出现的次数
 
while (matcher.find()) {// 是否匹配单词
 
word = matcher.group();// 得到一个单词-树映射的键
 
n++;// 单词数加1
 
if (myTreeMap.containsKey(word)) {// 如果包含该键，单词出现过
 
num = myTreeMap.get(word);// 得到单词出现的次数
 
Integer count = (Integer) num;// 强制转化
 
myTreeMap.put(word, new Integer(count.intValue() + 1));
 
} else {
 
myTreeMap.put(word, new Integer(1));// 否则单词第一次出现，添加到映射中
 
}
 
}
 
System.out.println("统计分析如下：");
 
System.out.println("文章中单词总数" + n + "个");
 
System.out.println("具体的信息在当前目录的result.txt文件中");
 
Iteratoriter = myTreeMap.keySet().iterator();// 得到树映射键集合的迭代器
 
Object key = null;
 
while (iter.hasNext()) {// 使用迭代器遍历树映射的键
 
key = iter.next();
 
bufw.write((String) key + ":" + myTreeMap.get(key));// 键/值写到文件中
 
bufw.newLine();
 
System.out.println((String) key + ":" + myTreeMap.get(key));
 
}
 
bufw.write("english.txt中的单词总数" + n + "个");
 
bufw.newLine();
 
bufw.write("english.txt中不同单词" + myTreeMap.size() + "个");
 
bufw.close();
 
}
 
}
 
总结：
 
这个程序包含了文本文件统计单词个数及去掉空行的方法…………
 
涵盖了 java正则表达(pattern类及matcher类)的用法 、Treemap、迭代器(iterater)、字符流写入写出等基础知识的用法
 
再列出个pattern类的小用法：
 
public class patternPractice {
 
private static final String REGEX = ":";
 
private static final String INPUT = "one:two:three:four:five";
 
public static void main(String[] args) throws IOException {
 
Pattern expression = Pattern.compile(REGEX);
 
String[] items = expression.split(INPUT);
 
int n = 0;
 
for (String s : items) {
 
System.out.println(s);
 
n++;
 
System.out.println(n);
 
}
 
}
 
}

 
importjava.io.BufferedReader;importjava.io.File;importjava.io.FileNotFoundException;importjava.io.FileReader;importjava.io.IOException;importjava.util.ArrayList;importjava.util.Collections;importjava.util.Comparator;importjava.util.HashMap;importjava.util.List;importjava.util.Map;importjava.util.Scanner;public classTongJiDanCi {public static void main(String[] args)throws IOException//扔掉很重要
 
{
 
File file= new File("D:/c1.txt");
 
System.out.println("0.统计英文字母个数及其百分比 1.统计英文单词个数");
 
Scanner sc= newScanner(System.in);int value=sc.nextInt();while(true) {switch(value) {case 0:txtString(file);case 1:txtString2(file);default:break;
 
}
 
}
 
}/** 统计字母*/
 
public static void txtString(File file) throwsIOException{try{//IO操作读取文件内容
 
FileReader fr = newFileReader(file);
 
@SuppressWarnings("resource")
 
BufferedReader br= new BufferedReader(fr);//构造一个BufferedReader类来读取文件
 
HashMap hm = new HashMap();//构建了一个新的HashMap对象，强制指定这个HashMap必须是以String为key, 以Integer为值。
 
String line =null;
 
Integer count= 0;//每个字母的个数
 
Integer total = 0;//统计字母总数，作百分比用
 
while ((line=br.readLine())!=null) {char[] ch = line.toCharArray();//将字符串对象中的字符转换为一个字符数组。
 
total = total +ch.length;for (int i = 0; i < ch.length; i++) {
 
ch[i]= Character.toLowerCase(ch[i]);//将大写字符转换为小写，小写字母不变
 
count = hm.get(ch[i]+"");//ch[i]+""的作用是加一个空格后，括号内转化为字符串
 
if (count == null) {
 
count=1;//只出现一次
 
}else{
 
count++;
 
}
 
hm.put(ch[i]+"", count);
 
}
 
}for (String str : hm.keySet()) {//设变量str获取键
 
System.out.println(str+"个数:"+hm.get(str)+" "+hm.get(str)*100.0/total+"%");
 
}
 
System.out.println("总字母个数："+total);//排序输出
 
List> list_Data = new ArrayList>(hm.entrySet());
 
Collections.sort(list_Data,new Comparator>(){public int compare(Map.Entry o1, Map.Entryo2)
 
{//o1 to o2升序 o2 to o1降序
 
returno2.getValue().compareTo(o1.getValue());
 
}
 
});
 
System.out.println("排序输出：");
 
System.out.println(hm);
 
}catch(FileNotFoundException e) {
 
e.printStackTrace();
 
}
 
}/** 统计单词*/
 
public static void txtString2(File file) throwsIOException{
 
FileReader fr= newFileReader(file);
 
BufferedReader br= new BufferedReader(fr);//构造一个BufferedReader类来读取文件
 
StringBuffer sb = newStringBuffer();
 
String line=null;while ((line=br.readLine())!=null){
 
sb.append(line);//将读取出的字符追加到stringbuffer中
 
}
 
fr.close();//关闭读入流
 
String str = sb.toString().toLowerCase(); //将stringBuffer转为字符并转换为小写
 
String[] words = str.split("[^(a-zA-Z)]+"); //非单词的字符来分割，得到所有单词
 
Map map = new HashMap() ;for(String word :words){if(map.get(word)==null){ //若不存在说明是第一次，则加入到map,出现次数为1
 
map.put(word,1);
 
}else{
 
map.put(word,map.get(word)+1); //若存在，次数累加1
 
}
 
}//排序
 
List> list = new ArrayList>(map.entrySet());
 
Comparator> comparator = new Comparator>() {public int compare(Map.Entry left, Map.Entryright) {int i=left.getValue()-right.getValue();if(i==0) {return(right.getKey().compareTo(left.getKey()));
 
}return(left.getValue().compareTo(right.getValue()));
 
}
 
};//集合默认升序
 
Collections.sort(list,comparator);int n=list.size();
 
System.out.println("一共有"+n+"种单词");
 
System.out.println("请输入你要排序前几个单词：");
 
Scanner scanner=newScanner(System.in);
 
n=scanner.nextInt();for(int i=0;i
 
System.out.println(list.get(list.size()-i-1).getKey() +":"+list.get(list.size()-i-1).getValue());
 
}
 
}
 
}

 
package test;
 
/*
 
* Task :统计文本英文单词总个数，并列出每个单词的个数
 
*
 
* Date：2014.02.26
 
*
 
*Author：璀若星辰
 
* */
 
import java.io.BufferedReader;
 
import java.io.File;
 
import java.io.FileInputStream;
 
import java.io.InputStreamReader;
 
import java.util.ArrayList;
 
import java.util.Collections;
 
import java.util.Comparator;
 
import java.util.List;
 
import java.util.Map;
 
import java.util.Map.Entry;
 
import java.util.TreeMap;
 
import java.util.regex.Matcher;
 
import java.util.regex.Pattern;
 
public class IO_Word {
 
public static ListIo_word(String str)throws Exception{
 
File file = new File(str);
 
int n = 0;//文章中单词总数
 
TreeMap myTreeMap = new TreeMap();//存放键值对
 
Object word = null;//文章中的单词
 
Object num = null;//出现的次数
 
FileInputStream fis = new FileInputStream(file);
 
try{
 
InputStreamReader isr = new InputStreamReader(fis, "gb2312");
 
try{
 
BufferedReader br = new BufferedReader(isr);
 
try{
 
List all = new ArrayList();
 
String temp = br.readLine();
 
while (temp !=null){
 
all.add(temp);
 
temp = br.readLine();
 
}
 
//System.out.println("all="+all.size());
 
// System.out.println(all.get(0));
 
Pattern expression = Pattern.compile("[a-zA-Z]+");//定义正则表达式匹配单词
 
String string1 = all.toString().toLowerCase();//转换成小写
 
Matcher matcher = expression.matcher(string1);//定义string1的匹配器
 
while(matcher.find()){
 
word = matcher.group();//得到一个单词—树映射的键
 
//System.out.println("word="+word);
 
n++;
 
if(myTreeMap.containsKey(word)){
 
num = myTreeMap.get(word);//得到单词出现的次数
 
Integer count = (Integer)num;
 
myTreeMap.put(word, new Integer(count.intValue()+1));
 
}else {
 
myTreeMap.put(word, new Integer(1));//否则单词第一次出现，添加到映射中
 
}
 
}
 
System.out.println("统计分析如下：");
 
System.out.println("txt文章中单词总数"+ n +"个");
 
/*Iterator iter = myTreeMap.keySet().iterator();//得到树映射键集合的迭代器
 
while(iter.hasNext()){
 
key = iter.next();
 
System.out.println(((String)key+"-"+myTreeMap.get(key)));
 
}*/
 
List> list = new ArrayList>(myTreeMap.entrySet());
 
System.out.println("list="+list.size());
 
Collections.sort(list,new Comparator>(){
 
public int compare(Map.Entryzj, Map.Entry zz) {
 
return (zz.getValue() - zj.getValue());
 
}
 
});
 
for (Entry entry : list) {
 
System.out.println(entry.getKey() + "-" + entry.getValue() );
 
}
 
return all;
 
}finally{
 
br.close();
 
}
 
}finally{
 
isr.close();
 
}
 
}finally{
 
fis.close();
 
}
 
}
 
public static void main(String[] args) {
 
try {
 
IO_Word.Io_word("D:/abc.txt");
 
} catch (Exception e) {
 
e.printStackTrace();
 
}
 
}
 
}
 
运行结果效果如下
 

 
原文：http://blog.csdn.net/u012631267/article/details/19975307